Copertina

CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mireshghallah, Niloofar, Mangaokar, Neal, Kokhlikyan, Narine, Zharmagambetov, Arman, Zaheer, Manzil, Mahloujifar, Saeed, Chaudhuri, Kamalika
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection
di: Wen, Yuxin, et al.
Pubblicazione: (2025)

SecAlign: Defending Against Prompt Injection with Preference Optimization
di: Chen, Sizhe, et al.
Pubblicazione: (2024)

Auditing $f$-Differential Privacy in One Run
di: Mahloujifar, Saeed, et al.
Pubblicazione: (2024)

Z0-Inf: Zeroth Order Approximation for Data Influence
di: Kokhlikyan, Narine, et al.
Pubblicazione: (2025)

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
di: Evtimov, Ivan, et al.
Pubblicazione: (2025)

Machine Learning with Privacy for Protected Attributes
di: Mahloujifar, Saeed, et al.
Pubblicazione: (2025)

Privacy Amplification for the Gaussian Mechanism via Bounded Support
di: Hu, Shengyuan, et al.
Pubblicazione: (2024)

Privacy Blur: Quantifying Privacy and Utility for Image Data Release
di: Mahloujifar, Saeed, et al.
Pubblicazione: (2025)

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
di: Mireshghallah, Niloofar, et al.
Pubblicazione: (2023)

Guarantees of confidentiality via Hammersley-Chapman-Robbins bounds
di: Chaudhuri, Kamalika, et al.
Pubblicazione: (2024)

Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection
di: Naseh, Ali, et al.
Pubblicazione: (2025)

Measuring Privacy Loss in Distributed Spatio-Temporal Data
di: Koga, Tatsuki, et al.
Pubblicazione: (2024)

Differentially Private Model Merging
di: Yin, Qichuan, et al.
Pubblicazione: (2026)

Position: Privacy Is Not Just Memorization!
di: Mireshghallah, Niloofar, et al.
Pubblicazione: (2025)

Detecting Benchmark Contamination Through Watermarking
di: Sander, Tom, et al.
Pubblicazione: (2025)

Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks
di: Chen, Sizhe, et al.
Pubblicazione: (2025)

Robustness of Locally Differentially Private Graph Analysis Against Poisoning
di: Imola, Jacob, et al.
Pubblicazione: (2022)

Metric Differential Privacy at the User-Level Via the Earth Mover's Distance
di: Imola, Jacob, et al.
Pubblicazione: (2024)

Communication-Efficient Triangle Counting under Local Differential Privacy
di: Imola, Jacob, et al.
Pubblicazione: (2021)

Can We Infer Confidential Properties of Training Data from LLMs?
di: Huang, Pengrun, et al.
Pubblicazione: (2025)

DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
di: Wang, Erchi, et al.
Pubblicazione: (2026)

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
di: Paulus, Anselm, et al.
Pubblicazione: (2024)

CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents
di: Fu, Wenjie, et al.
Pubblicazione: (2026)

Observational Auditing of Label Privacy
di: Kalemaj, Iden, et al.
Pubblicazione: (2025)

PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
di: Mangaokar, Neal, et al.
Pubblicazione: (2024)

Integrating Differential Privacy and Contextual Integrity
di: Benthall, Sebastian, et al.
Pubblicazione: (2024)

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
di: Park, Sangwoo, et al.
Pubblicazione: (2026)

Defending Object Detectors against Patch Attacks with Out-of-Distribution Smoothing
di: Feng, Ryan, et al.
Pubblicazione: (2022)

Differentially Private Learning Needs Better Model Initialization and Self-Distillation
di: Ngong, Ivoline C., et al.
Pubblicazione: (2024)

Can Large Language Models Really Recognize Your Name?
di: Pham, Dzung, et al.
Pubblicazione: (2025)

A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
di: Panda, Ashwinee, et al.
Pubblicazione: (2022)

Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
di: Koga, Tatsuki, et al.
Pubblicazione: (2024)

PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases
di: Bae, Yubeen, et al.
Pubblicazione: (2025)

Private Fine-tuning of Large Language Models with Zeroth-order Optimization
di: Tang, Xinyu, et al.
Pubblicazione: (2024)

Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training
di: Borkar, Jaydeep, et al.
Pubblicazione: (2025)

What Really is a Member? Discrediting Membership Inference via Poisoning
di: Mangaokar, Neal, et al.
Pubblicazione: (2025)

FairProof : Confidential and Certifiable Fairness for Neural Networks
di: Yadav, Chhavi, et al.
Pubblicazione: (2024)

On Differentially Private U Statistics
di: Chaudhuri, Kamalika, et al.
Pubblicazione: (2024)

ExpProof : Operationalizing Explanations for Confidential Models with ZKPs
di: Yadav, Chhavi, et al.
Pubblicazione: (2025)

Taming Data Challenges in ML-based Security Tasks Using Generative AI
di: Kanchi, Shravya, et al.
Pubblicazione: (2025)